Triple
T31628770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Codogno |
E807099
|
entity |
| Predicate | COVID-19FirstCaseDate |
P56456
|
FINISHED |
| Object | February 2020 |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: February 2020 | Statement: [Codogno, COVID-19FirstCaseDate, February 2020]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: COVID-19FirstCaseDate Context triple: [Codogno, COVID-19FirstCaseDate, February 2020]
-
A.
officiallyConfirmedIn
Indicates that something has been formally acknowledged or validated within an official document, statement, or process.
-
B.
yearOfOutbreak
chosen
Indicates the specific calendar year in which an outbreak began or was first identified.
-
C.
firstQuarantineEnd
Indicates the point in time or event when an entity’s initial quarantine period concludes.
-
D.
lastEndemicCaseCountry
Indicates the country in which the most recent known endemic case of a disease or condition occurred.
-
E.
initiallyEndemicCountries
Indicates the set of countries in which something (typically a disease or species) was originally endemic at the start of the period or process being considered.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f348d7883c8190b6c13ab92b7ef076 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a8e303148190b0f8959045db3073 |
completed | May 3, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69f6a757c6e081908e37631e5d8d246b |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 10:44 p.m.